INDEX

Explanations

terms related to descriptions and assessments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ngh

-0.14

çľŁæŃ£

-0.14

Ø¦Ø©

-0.14

emey

-0.14

vac

-0.14

vais

-0.14

aseline

-0.14

URY

-0.14

asje

-0.14

oine

-0.13

POSITIVE LOGITS

 thus

0.47

thus

0.42

Thus

0.38

 Thus

0.36

 differently

0.34

 saying

0.26

 cosÃ¬

0.25

 ainsi

0.25

 asÃŃ

0.24

 accordingly

0.24

Activations Density 0.139%

terms related to descriptions and assessments

No Comments

No Known Activations